Online milk composition analysis with an on-farm near-infrared sensor

Abstract

On-farm monitoring of milk composition can support close control of the udder and metabolic health of individual dairy cows. In previous studies, near-infrared (NIR) spectroscopy applied to milk analysis has proven useful for predicting the main components of raw milk (fat, protein, and lactose). In this contribution, we present and evaluate a precise tool for online milk composition analysis on the farm. For each milking, the online analyzer automatically collects and analyses a representative milk sample. The system acquires the NIR transmission spectra of the milk samples in the wavelength range from 960 to 1690 nm and performs a milk composition prediction afterward. Over a testing period of 8 weeks, the sensor collected 1165 NIR transmittance spectra of raw milk samples originating from 36 cows for which reference chemical analyses were performed for fat, protein, and lactose. For the same online sensor system, two calibration scenarios were evaluated: training posthoc prediction models based on a representative set of calibration samples (n = 319) acquired over the

An Overview on the Use of Near Infrared Spectroscopy (NIRS) on Farms for the Management of Dairy Cows

“…The prediction ability of NIRS instruments on non-homogenized milk has been supported by recent studies [103,104]. Results indicated that NIRS may be used to determine milk quality in real-time during milking by providing information to farmers on milk characteristics and on physiological conditions of every cow [99,100].…”

“…However, most of the research was carried out on milk in off-line mode or rather not directly in the milking parlor. Recently, tests have been carried out using NIRS directly in the milking parlors to have individual check of each animal and to obtain information on milk quality and health status of the cows [8,93,[99][100][101][102][103][104]. Pioneering studies on the possibility of using NIRS instruments on farm were carried out by Tsenkova et al [87].…”

“…Applying NIRS prediction systems on automatic milking robots (AMS), Kawasaki et al [100] obtained slightly poorer results for the prediction of many milk parameters. Diaz-Olivares et al [99] by applying a NIRS detector on AMS capable of automatically collecting and analyzing a milk sample for each milking, obtained satisfactory results for the prediction of fat and protein (R 2 > 0.89), poor prediction for lactose (R 2 = 0.64). In-line applications, reported by Melfsen et al [93], showed very high predictive capabilities for fat, proteins, and lactose and satisfactory for the content of milk urea and SCC.…”

Multifunctional Composites

“…In contrast to the off-line milk analyzers based on FTIR spectrometers working in the MIR spectral region, NIR technology allows developing portable devices for fast on-farm milk quality control [95] and analytical solutions for in-line applications in milking robots [96] and automated milking systems [97]. Authors claim that such devices can determine the concentrations of three major milk constituents (fat, protein, and lactose) and somatic cells count with accuracy which is quite acceptable for practical use.…”

Grand Challenges to Livestock Physiology and Management

“…Advances in imaging, automation, sensors, electronic data exchange through "the cloud, " and data analytics offer extensive opportunities for specific interventions best aligned with physiological state and external inputs, even for animals housed under comingled conditions. Robotic milking and in-line milk composition analysis, for example, offer repeated opportunities to assess the cow's productive state and health (Diaz-Olivares et al, 2020;Michie et al, 2020). Could these data also be harnessed to indicate the affective state of the cow?…”